Increase default retries;Add healthcheck

ansible/roles/firstboot/files/ansible_payload/bootstrap/roles/workloadcluster/tasks/clusterapi.yml

@@ -99,7 +99,7 @@
         --kubeconfig {{ kubeconfig.path }}
     chdir: /opt/metacluster/cluster-api
 
-- name: Ensure CAPI/CAPV controller availability
+- name: Ensure controller availability
   kubernetes.core.k8s_info:
     kind: Deployment
     name: "{{ item.name }}"
@@ -107,6 +107,8 @@
     wait: true
     kubeconfig: "{{ kubeconfig.path }}"
   loop:
+    - name: caip-in-cluster-controller-manager
+      namespace: caip-in-cluster-system
     - name: capi-controller-manager
       namespace: capi-system
     - name: capv-controller-manager

ansible/roles/firstboot/files/ansible_payload/common/vars/defaults.yml

@@ -1,5 +1,5 @@
 playbook:
-  retries: 5
+  retries: 10
   delay:
     # These values are multiplied with the value of `storage_benchmark`
     long: 2